Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of existential or subjective commentary within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulk
    -0.15
    icies
    -0.14
    ез
    -0.14
    inkel
    -0.14
    .twitch
    -0.13
     cru
    -0.13
     endregion
    -0.13
    ॰
    -0.13
    ys
    -0.13
    232
    -0.13
    POSITIVE LOGITS
     yet
    0.23
     exactly
    0.20
     Exhibit
    0.20
     like
    0.20
     nothing
    0.20
     grounds
    0.19
     proof
    0.19
    akin
    0.19
    tant
    0.19
     precisely
    0.19
    Act Density 0.460%

    No Known Activations